BERT-pytorch
coref
BERT-pytorch | coref | |
---|---|---|
1 | 2 | |
6,018 | 433 | |
- | - | |
0.0 | 0.0 | |
8 months ago | over 1 year ago | |
Python | Python | |
Apache License 2.0 | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
BERT-pytorch
-
Lack of activation in transformer feedforward layer?
I'm curious as to why the second matrix multiplication is not followed by an activation unlike the first one. Is there any particular reason why a non-linearity would be trivial or even avoided in the second operation? For reference, variations of this can be witnessed in a number of different implementations, including BERT-pytorch and attention-is-all-you-need-pytorch.
coref
-
[Discussion] Are there masked LMs that can fill in multiple tokens per mask token?
Found relevant code at https://github.com/mandarjoshi90/coref + all code implementations here
-
Best textbook on coreference stuff?
For software, you'll probably be interested in e2e-coref + SpanBERT: https://github.com/mandarjoshi90/coref (state-of-the-art I'd say, more or less)
What are some alternatives?
haystack - :mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
pronomial - pronomial postag/word_gender based coreference solver
bertviz - BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)
transformers - π€ Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
transformer-pytorch - Transformer: PyTorch Implementation of "Attention Is All You Need"
PaddleNLP - π Easy-to-use and powerful NLP and LLM library with π€ Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including πText Classification, π Neural Search, β Question Answering, βΉοΈ Information Extraction, π Document Intelligence, π Sentiment Analysis etc.
Transformers4Rec - Transformers4Rec is a flexible and efficient library for sequential and session-based recommendation and works with PyTorch.
scibert - A BERT model for scientific text.
cuad - CUAD (NeurIPS 2021)
attention-is-all-you-need-pytorch - A PyTorch implementation of the Transformer model in "Attention is All You Need".